TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking

arXiv:2312.08514v2 Announce Type: replace
Abstract: Video Object Segmentation (VOS) has emerged as an increasingly important problem with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings), depicting small objects undergoing both rigid and non-rigid (including state) deformations. While a number of recent approaches have been explored for this task, these data characteristics still present challenges. In this work we propose a novel, clip-based DETR-style encoder-decoder architecture, which focuses …

abstract arxiv availability cs.cv datasets global object objects scale segmentation small state tracking transformation transformer type video videos